Long context

DeepSeek V4 Flash API pricing

DeepSeek's models — cost-efficient reasoning and coding.

Model IDdeepseek-v4-flash

ChatStreamingTool calling

Get API Key Run your first request

Call summary

Input

$0.60/ 1M tokens

Cache write $0.60

Cache read $0.012

Output

$2.40/ 1M tokens

Context Window

API Endpoints

DeepSeek V4 Flash API endpoints

One API key — call this model through any of the 3 endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Chat Completions reference

POST/v1/messagesAnthropic-native · Native for Claude Code

Messages API reference

POST/v1/responsesResponses API · Native for Codex CLI

Responses API reference

Call DeepSeek V4 Flash from your code

The same API key works across all 3 endpoints below.

Endpoint

/v1/chat/completions

Model ID

deepseek-v4-flash

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

100.00%

Success 2xx

100.00%

Rate limit 429

0.00%

Server 5xx

0.00%

TPS

248.88

tokens/s

Avg. time to first token

2.36 s

Avg. latency

5.39 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Nov 5, 2026, 4:28 AM UTC

More DeepSeek models on Router One

1 other DeepSeek model on the same gateway and API key — its page lists endpoints, posted price, and context window.

DeepSeek V4.1 Flash$0.60 in / $2.40 out per 1M1M context

DeepSeek V4 Flash at a glance

DeepSeek V4 Flash (model ID deepseek-v4-flash) is a DeepSeek-series text model on Router One. Posted rate: $0.60 in / $2.40 out per 1M tokens. Router One subscriptions include DeepSeek V4 Flash in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Context window: 1M tokens. Accepts text; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-native, the Claude Code path), POST /v1/responses (Responses API, the Codex CLI path).

DeepSeek V4 Flash FAQ

How much does DeepSeek V4 Flash cost on Router One?

DeepSeek V4 Flash is billed per token on Router One: $0.60 in / $2.40 out per 1M tokens, pay as you go.

Is DeepSeek V4 Flash included in Router One subscriptions?

Router One subscriptions include DeepSeek V4 Flash in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates.

Which endpoints serve DeepSeek V4 Flash?

DeepSeek V4 Flash is served on 3 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-native, the Claude Code path), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.

What is DeepSeek V4 Flash's context window?

DeepSeek V4 Flash accepts up to 1M tokens of context per request on Router One.

Start using DeepSeek V4 Flash

Create an API key and call DeepSeek V4 Flash at $0.60 in / $2.40 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide OpenAI-compatible API